{"id":119,"date":"2026-08-06T00:31:23","date_gmt":"2026-08-05T16:31:23","guid":{"rendered":"https:\/\/ltrainyard.icu\/?p=119"},"modified":"2026-08-06T00:46:14","modified_gmt":"2026-08-05T16:46:14","slug":"day-26-%e7%bd%91%e7%bb%9c%e7%88%ac%e8%99%ab%ef%bc%9arequests-%e4%b8%8e-beautifulsoup","status":"publish","type":"post","link":"https:\/\/ltrainyard.icu\/index.php\/2026\/08\/06\/day-26-%e7%bd%91%e7%bb%9c%e7%88%ac%e8%99%ab%ef%bc%9arequests-%e4%b8%8e-beautifulsoup\/","title":{"rendered":"| Day 26 | \u7f51\u7edc\u722c\u866b\uff1arequests \u4e0e BeautifulSoup |"},"content":{"rendered":"\n<h3 class=\"wp-block-heading\">1 requests \u4e0e Response \u5bf9\u8c61 \u2014\u2014 \u722c\u866b\u7684\u7b2c\u4e00\u6b65<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u662f\u4ec0\u4e48\uff1f\u4e3a\u4ec0\u4e48\u5b66\uff1f<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>requests<\/strong> \u662f Python \u6700\u6d41\u884c\u7684 HTTP \u8bf7\u6c42\u5e93\u3002\u722c\u866b\u7684\u7b2c\u4e00\u6b65\u6c38\u8fdc\u662f\u300c\u628a\u7f51\u9875\u62ff\u56de\u6765\u300d\uff1a<code>requests.get(url)<\/code> \u5411\u670d\u52a1\u5668\u53d1\u8bf7\u6c42\uff0c\u8fd4\u56de <strong>Response \u5bf9\u8c61<\/strong>\uff0c\u91cc\u9762\u88c5\u7740\u72b6\u6001\u7801\u3001\u7f51\u9875\u6587\u672c\u3001\u7f16\u7801\u3002\u6240\u6709\u722c\u866b\u548c API \u8c03\u7528\u90fd\u4ee5\u5b83\u4e3a\u8d77\u70b9\u3002\u6211\u4eec\u6bcf\u5929\u4e0a\u7f51\u770b\u5230\u7684\u7f51\u9875\uff0c\u672c\u8d28\u662f\u4e00\u5806 HTML \u6587\u672c\u3002<strong>\u722c\u866b\u5c31\u662f\u300c\u7528\u7a0b\u5e8f\u4ee3\u66ff\u4eba\u53bb\u770b\u7f51\u9875\u300d<\/strong>\uff1a\u5148\u8bf7\u6c42\u7f51\u9875\u62ff\u5230 HTML\uff0c\u518d\u4ece HTML \u91cc\u628a\u60f3\u8981\u7684\u4fe1\u606f\u6311\u51fa\u6765\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u5e95\u5c42\u539f\u7406<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><code>requests.get(url)<\/code> \u5185\u90e8\uff1a\u5efa\u7acb\u8fde\u63a5 \u2192 \u53d1\u9001\u8bf7\u6c42\u5934 \u2192 \u670d\u52a1\u5668\u8fd4\u56de\u54cd\u5e94 \u2192 \u5c01\u88c5\u6210 <code>Response<\/code>\u3002\u4e09\u4e2a\u5e38\u7528\u5c5e\u6027\uff1a<code>resp.status_code<\/code>\uff08<code>200<\/code> \u6210\u529f\u3001<code>404<\/code> \u4e0d\u5b58\u5728\u3001<code>403<\/code> \u88ab\u62d2\uff09\u3001<code>resp.text<\/code>\uff08\u7f51\u9875\u6e90\u7801\uff09\u3001<code>resp.encoding<\/code>\uff08\u7f16\u7801\uff0c\u4e0d\u5bf9\u4e2d\u6587\u5c31\u4e71\u7801\uff09\u3002**\u7f51\u7edc\u4e0d\u53ef\u9760\uff0c\u8981\u52a0 <code>timeout<\/code> \u548c <code>try\/except<\/code>**\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u751f\u6d3b\u7c7b\u6bd4<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u50cf<strong>\u6253\u7535\u8bdd<\/strong>\uff1a<code>requests.get(url)<\/code> \u662f\u62e8\u53f7\u52a0\u95ee\u8bdd\uff0cResponse \u662f\u5bf9\u65b9\u7b54\u590d\u2014\u2014\u5148\u542c\u8bed\u6c14\uff08200 \u662f\u300c\u597d\u7684\u300d\uff09\uff0c\u518d\u542c\u5185\u5bb9\uff08<code>resp.text<\/code>\uff09\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u6ce8\u610f\u4e8b\u9879\u603b\u7ed3<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">1 <strong>\u8bf7\u6c42\u7f51\u9875\uff0c\u770b\u72b6\u6001\u7801\u4e0e\u5185\u5bb9<\/strong>\uff08\u9700\u8981\u8054\u7f51\uff09\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>import requests\n\nresp = requests.get(\"https:\/\/example.com\", timeout=10)\nprint(\"\u72b6\u6001\u7801\uff1a\", resp.status_code)      # 200 \u8868\u793a\u6210\u529f\nprint(\"\u7f16\u7801\uff1a\", resp.encoding)\nprint(\"\u7f51\u9875\u524d 80 \u4e2a\u5b57\u7b26\uff1a\")\nprint(resp.text&#91;:80])\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\"><code>requests.get(\"https:\/\/example.com\", timeout=10)<\/code> \u53d1\u8bf7\u6c42\uff08<code>timeout=10<\/code> \u662f\u8d85\u65f6\u4fdd\u62a4\uff09\uff1b<code>resp.status_code<\/code> \u5224\u65ad\u6210\u8d25\uff1b<code>resp.text<\/code> \u662f HTML \u6e90\u7801\u2014\u2014\u8fd9\u5c31\u662f\u722c\u866b\u7684\u300c\u539f\u6599\u300d\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">2 <strong>\u52a0 User-Agent + \u624b\u52a8\u6307\u5b9a\u7f16\u7801<\/strong>\uff08\u4e2d\u6587\u4e0d\u4e71\u7801\u7684\u5173\u952e\uff09\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>headers = {\n    \"User-Agent\": \"Mozilla\/5.0 (Windows NT 10.0; Win64; x64) \"\n                  \"AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/120.0 Safari\/537.36\"\n}\nresp = requests.get(\"https:\/\/www.weather.com.cn\/weather\/101010100.shtml\", headers=headers, timeout=10)\nresp.encoding = \"utf-8\"     # \u624b\u52a8\u6307\u5b9a\u7f16\u7801\uff0c\u4e2d\u6587\u624d\u4e0d\u4f1a\u4e71\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u5f88\u591a\u7f51\u7ad9\u4f1a\u68c0\u67e5\u8bf7\u6c42\u6765\u6e90\uff0c\u4e0d\u5e26\u6d4f\u89c8\u5668\u6807\u8bc6\uff08User-Agent\uff09\u53ef\u80fd\u88ab\u62d2\u3002\u7f51\u9875\u53ef\u80fd\u662f UTF-8 \u7684\uff0c\u4f46 requests \u53ef\u80fd\u731c\u9519\u7f16\u7801\uff0c<strong>\u624b\u52a8\u6307\u5b9a <code>resp.encoding = \"utf-8\"<\/code><\/strong> \u4e2d\u6587\u624d\u4e0d\u4e71\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u6613\u9519\u70b9<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u9519\u8bef\u5199\u6cd5\uff1a\u4e0d\u5199 <code>timeout<\/code> \u2192 \u95ee\u9898\uff1a\u670d\u52a1\u5668\u4e0d\u54cd\u5e94\u65f6\u65e0\u9650\u5361\u4f4f \u2192 \u6b63\u786e\u5199\u6cd5\uff1a<code>requests.get(url, timeout=10)<\/code>\u3002<\/li>\n\n\n\n<li>\u9519\u8bef\u5199\u6cd5\uff1aURL \u5fd8\u4e86 <code>https:\/\/<\/code> \u2192 \u95ee\u9898\uff1a\u62a5 <code>InvalidURL<\/code> \/ <code>MissingSchema<\/code> \u2192 \u6b63\u786e\u5199\u6cd5\uff1aURL \u5199\u5168\uff1a<code>https:\/\/example.com<\/code>\u3002<\/li>\n\n\n\n<li>\u9519\u8bef\u5199\u6cd5\uff1a\u4e2d\u6587\u4e71\u7801 \u2192 \u95ee\u9898\uff1a\u7f51\u9875\u7f16\u7801\u6ca1\u8bbe\u5bf9 \u2192 \u6b63\u786e\u5199\u6cd5\uff1a\u624b\u52a8\u6307\u5b9a <code>resp.encoding = \"utf-8\"<\/code>\u3002<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u8bb0\u5fc6\u53e3\u8bc0<\/strong>\uff1aget \u62ff\u7f51\u9875\uff0cresp \u662f\u7b54\u590d\uff1b200 \u662f\u6210\u529f\uff0c404 \u6ca1\u4eba\u63a5\uff1b\u8d85\u65f6\u515c\u5e95\u522b\u5fd8 try\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">2 BeautifulSoup \u5bf9\u8c61\u6811 \u2014\u2014 \u628a HTML \u53d8\u6210\u300c\u6863\u6848\u67dc\u300d<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u662f\u4ec0\u4e48\uff1f\u4e3a\u4ec0\u4e48\u5b66\uff1f<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>BeautifulSoup\uff08bs4\uff09<\/strong> \u662f\u89e3\u6790 HTML \u7684\u5e93\u3002\u7f51\u9875\u6e90\u7801\u662f\u4e00\u5927\u5768\u5b57\u7b26\u4e32\uff0c\u76f4\u63a5\u5207\u7247\u63d0\u53d6\u975e\u5e38\u75db\u82e6\uff1bBeautifulSoup \u628a HTML <strong>\u89e3\u6790\u6210\u4e00\u68f5\u5bf9\u8c61\u6811<\/strong>\uff08\u6807\u7b7e\u7684\u5d4c\u5957\u7ed3\u6784\uff09\uff0c\u4e4b\u540e\u7528\u300c\u627e\u6807\u7b7e\u300d\u7684\u65b9\u5f0f\u53d6\u5185\u5bb9\u3002\u914d\u5408 requests \u5c31\u662f\u5b8c\u6574\u7684\u300c\u6293\u53d6 + \u89e3\u6790\u300d\u94fe\u8def\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u5e95\u5c42\u539f\u7406<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><code>BeautifulSoup(html, \"html.parser\")<\/code> \u628a\u5b57\u7b26\u4e32\u53d8\u6210\u5bf9\u8c61\u6811\uff1a\u6bcf\u4e2a\u6807\u7b7e\u662f\u4e00\u4e2a <code>Tag<\/code> \u5bf9\u8c61\u3002\u5e38\u7528\u64cd\u4f5c\uff1a<code>soup.find(\"h1\")<\/code> \u627e\u7b2c\u4e00\u4e2a\u3001<code>soup.find_all(\"li\")<\/code> \u627e<strong>\u6240\u6709<\/strong>\u3001<code>tag.get_text()<\/code> \u53d6\u6587\u5b57\u3001<code>tag[\"href\"]<\/code> \u53d6\u5c5e\u6027\u3002**\u6ce8\u610f <code>class<\/code> \u662f Python \u5173\u952e\u5b57\uff0c\u6309 class \u67e5\u627e\u8981\u5199 <code>class_<\/code>**\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u751f\u6d3b\u7c7b\u6bd4<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u50cf<strong>\u6863\u6848\u7ba1\u7406\u5458<\/strong>\uff1aHTML \u662f\u4e00\u5806\u6742\u4e71\u7684\u7eb8\uff08\u5b57\u7b26\u4e32\uff09\uff0c\u7ba1\u7406\u5458\u6574\u7406\u6210\u6863\u6848\u67dc\uff08\u5bf9\u8c61\u6811\uff09\u2014\u2014\u627e\u300c\u6240\u6709\u6807\u9898\u300d\u67e5 <code>find_all(\"h2\")<\/code>\uff0c\u51e0\u79d2\u641e\u5b9a\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u6ce8\u610f\u4e8b\u9879\u603b\u7ed3<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">1 <strong>\u89e3\u6790\u672c\u5730 HTML\uff0c\u63d0\u53d6\u6807\u9898\u3001\u5217\u8868\u9879\u3001\u94fe\u63a5<\/strong>\uff08\u79bb\u7ebf\u53ef\u8dd1\uff09\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from bs4 import BeautifulSoup\n\nhtml = \"\"\"\n&lt;html&gt;&lt;body&gt;\n&lt;h1&gt;\u4eca\u65e5\u5929\u6c14&lt;\/h1&gt;\n&lt;ul&gt;\n  &lt;li&gt;\u5468\u4e00 \u6674 32\u2103&lt;\/li&gt;\n  &lt;li&gt;\u5468\u4e8c \u591a\u4e91 30\u2103&lt;\/li&gt;\n&lt;\/ul&gt;\n&lt;a href=\"\/detail\"&gt;\u67e5\u770b\u8be6\u60c5&lt;\/a&gt;\n&lt;\/body&gt;&lt;\/html&gt;\n\"\"\"\nsoup = BeautifulSoup(html, \"html.parser\")\nprint(soup.find(\"h1\").get_text())              # \u7b2c\u4e00\u4e2a h1 \u7684\u6587\u5b57\nfor item in soup.find_all(\"li\"):               # \u6240\u6709 li \u6807\u7b7e\n    print(item.get_text())\nprint(soup.find(\"a\")&#91;\"href\"])                  # \u53d6 a \u7684\u94fe\u63a5\u5c5e\u6027\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u8fd0\u884c\u7ed3\u679c\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>\u4eca\u65e5\u5929\u6c14\n\u5468\u4e00 \u6674 32\u2103\n\u5468\u4e8c \u591a\u4e91 30\u2103\n\/detail\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\"><code>BeautifulSoup(html, \"html.parser\")<\/code> \u628a\u5b57\u7b26\u4e32\u89e3\u6790\u6210\u5bf9\u8c61\u6811\uff08<strong>\u5fc5\u987b\u4f20\u89e3\u6790\u5668\u53c2\u6570<\/strong>\uff09\uff1b<code>soup.find(\"h1\")<\/code> \u627e\u7b2c\u4e00\u4e2a h1\uff0c<code>.get_text()<\/code> \u53d6\u6587\u5b57\uff1b<code>find_all(\"li\")<\/code> \u8fd4\u56de\u5217\u8868\u914d\u5408 for \u5faa\u73af\uff1b<code>[\"href\"]<\/code> \u53d6\u5c5e\u6027\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u6613\u9519\u70b9<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u9519\u8bef\u5199\u6cd5\uff1a<code>soup.find(\"p\", class=\"temp\")<\/code> \u2192 \u95ee\u9898\uff1a<code>class<\/code> \u662f\u5173\u952e\u5b57\uff0c\u8bed\u6cd5\u62a5\u9519 \u2192 \u6b63\u786e\u5199\u6cd5\uff1a\u7528 <code>class_=\"temp\"<\/code>\u3002<\/li>\n\n\n\n<li>\u9519\u8bef\u5199\u6cd5\uff1a<code>soup.find(...)<\/code> \u6ca1\u627e\u5230\u5c31 <code>.get_text()<\/code> \u2192 \u95ee\u9898\uff1a\u8fd4\u56de <code>None<\/code>\uff0c\u62a5 <code>AttributeError<\/code> \u2192 \u6b63\u786e\u5199\u6cd5\uff1a\u5148\u5224\u65ad <code>if tag is not None:<\/code>\u3002<\/li>\n\n\n\n<li>\u9519\u8bef\u5199\u6cd5\uff1a<code>BeautifulSoup(html)<\/code> \u4e0d\u5199\u89e3\u6790\u5668 \u2192 \u95ee\u9898\uff1a\u544a\u8b66\u300c\u672a\u6307\u5b9a\u89e3\u6790\u5668\u300d \u2192 \u6b63\u786e\u5199\u6cd5\uff1a\u663e\u5f0f\u5199 <code>BeautifulSoup(html, \"html.parser\")<\/code>\u3002<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u8bb0\u5fc6\u53e3\u8bc0<\/strong>\uff1aBeautifulSoup \u5efa\u6863\u6848\uff0cfind \u4e00\u4e2a find_all \u4e00\u5806\uff1bclass \u52a0\u4e0b\u5212\u7ebf\uff0ctext \u53d6\u6587\u672c\uff0cNone \u8981\u5148\u5224\u65ad\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">3 CSS \u9009\u62e9\u5668\u4e0e\u5217\u8868\u722c\u53d6\u5957\u8def \u2014\u2014 \u7cbe\u786e\u5b9a\u4f4d\u3001\u6279\u91cf\u63d0\u53d6<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u662f\u4ec0\u4e48\uff1f\u4e3a\u4ec0\u4e48\u5b66\uff1f<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><code>find<\/code> \/ <code>find_all<\/code> \u53ea\u80fd\u6309\u6807\u7b7e\u540d\u6216\u5355\u4e2a\u5c5e\u6027\u627e\uff0c\u590d\u6742\u9875\u9762\u4e0d\u591f\u7528\u3002<strong>CSS \u9009\u62e9\u5668<\/strong>\u662f\u7f51\u9875\u5f00\u53d1\u7684\u6807\u51c6\u5b9a\u4f4d\u8bed\u6cd5\uff1b\u800c\u65b0\u95fb\u3001\u5546\u54c1\u3001\u7535\u5f71\u7b49<strong>\u51e0\u4e4e\u6240\u6709\u5217\u8868\u9875\u7ed3\u6784\u76f8\u540c<\/strong>\u2014\u2014\u4e00\u4e2a\u5bb9\u5668\u91cc\u91cd\u590d N \u4e2a\u6761\u76ee\u3002\u5b66\u4f1a\u9009\u62e9\u5668 + \u300c\u5148\u9009\u6761\u76ee\u3001\u518d\u53d6\u5b57\u6bb5\u300d\uff0c\u4efb\u4f55\u5217\u8868\u9875\u90fd\u80fd\u722c\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u5e95\u5c42\u539f\u7406<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u9009\u62e9\u5668\u8bed\u6cd5\uff1a<code>\u6807\u7b7e<\/code> \u6309\u6807\u7b7e\u540d\u3001<code>#id<\/code> \u6309 id\uff08\u5982 <code>#tq_zx<\/code>\uff09\u3001<code>.class<\/code> \u6309 class\uff08\u5982 <code>.wea<\/code>\uff09\u3001<code>\u7a7a\u683c<\/code> \u8868\u793a\u300c\u91cc\u9762\u7684\u300d\uff08\u540e\u4ee3\uff09\u3002<code>soup.select(\"\u9009\u62e9\u5668\")<\/code> \u8fd4\u56de<strong>\u6240\u6709<\/strong>\u5339\u914d\uff08\u5217\u8868\uff09\uff1b<code>soup.select_one(\"\u9009\u62e9\u5668\")<\/code> \u8fd4\u56de<strong>\u7b2c\u4e00\u4e2a<\/strong>\uff08\u6ca1\u6709\u5219 <code>None<\/code>\uff09\u3002\u5217\u8868\u722c\u53d6\u4e24\u6b65\u8d70\uff1a\u5916\u5c42 <code>select<\/code> \u62ff\u6240\u6709\u6761\u76ee\uff0c\u5185\u5c42 <code>select_one<\/code> \u53d6\u6bcf\u4e2a\u5b57\u6bb5\uff1b<code>get_text(strip=True)<\/code> \u81ea\u52a8\u53bb\u9996\u5c3e\u7a7a\u767d\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u751f\u6d3b\u7c7b\u6bd4<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u50cf<strong>\u5feb\u9012\u67dc\u53d6\u4ef6\u7801<\/strong>\uff1a<code>#tq_zx<\/code> \u662f\u300c3 \u53f7\u67dc\uff08id\uff09\u300d\uff0c<code>.wea<\/code> \u662f\u300c\u84dd\u8272\u6807\u7b7e\u7684\u683c\u5b50\uff08class\uff09\u300d\uff0c<code>ul.t li<\/code> \u662f\u300c1 \u533a\u67dc\u5b50\u91cc\u7b2c\u4e8c\u5c42\u7684\u5305\u88f9\u300d\u3002\u518d\u50cf<strong>\u6574\u7406\u901a\u8baf\u5f55<\/strong>\uff1a\u5148\u62bd\u51fa\u6574\u672c\uff08select \u62ff\u6761\u76ee\uff09\uff0c\u518d\u9010\u9875\u6284\u59d3\u540d\u7535\u8bdd\uff08\u6bcf\u6761\u76ee\u53d6\u5b57\u6bb5\uff09\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u6ce8\u610f\u4e8b\u9879\u603b\u7ed3<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">1 <strong>CSS \u9009\u62e9\u5668\u5b9a\u4f4d\u6a21\u62df\u7684\u5929\u6c14\u5217\u8868<\/strong>\uff08\u79bb\u7ebf\u53ef\u8dd1\uff09\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from bs4 import BeautifulSoup\n\nhtml = \"\"\"\n&lt;ul class=\"t clearfix\"&gt;\n  &lt;li class=\"sky\"&gt;\n    &lt;h1&gt;3\u65e5\uff08\u4eca\u5929\uff09&lt;\/h1&gt;\n    &lt;p class=\"wea\"&gt;\u96f7\u9635\u96e8&lt;\/p&gt;\n    &lt;p class=\"tem\"&gt;&lt;span&gt;32&lt;\/span&gt;\/&lt;i&gt;24\u2103&lt;\/i&gt;&lt;\/p&gt;\n  &lt;\/li&gt;\n&lt;\/ul&gt;\n\"\"\"\n\nsoup = BeautifulSoup(html, \"html.parser\")\nli = soup.select_one(\"ul.t li\")            # class=t \u7684 ul \u91cc\u7b2c\u4e00\u4e2a li\nprint(li.select_one(\"h1\").get_text())      # \u65e5\u671f\nprint(li.select_one(\"p.wea\").get_text())   # \u5929\u6c14\uff08class=wea\uff09\nprint(li.select_one(\"span\").get_text())    # \u6700\u9ad8\u6e29\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u8fd0\u884c\u7ed3\u679c\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>3\u65e5\uff08\u4eca\u5929\uff09\n\u96f7\u9635\u96e8\n32\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\"><code>\"ul.t li\"<\/code> \u662f CSS \u9009\u62e9\u5668\uff08<code>ul<\/code> \u52a0 <code>.t<\/code> \u8868\u793a class \u4e3a t \u7684 ul\uff0c\u7a7a\u683c\u540e <code>li<\/code> \u8868\u793a\u91cc\u9762\u7684 li\uff09\uff1b<code>select_one<\/code> \u53ea\u53d6\u7b2c\u4e00\u4e2a\uff1b\u62ff\u5230 <code>li<\/code> \u540e <code>li.select_one(...)<\/code> \u5728<strong>\u5c40\u90e8<\/strong>\u7ee7\u7eed\u627e\u2014\u2014\u5143\u7d20\u4e0a\u4e5f\u80fd\u8c03\u540c\u6837\u7684\u65b9\u6cd5\uff0c\u8fd9\u662f\u722c\u866b\u5e38\u7528\u6280\u5de7\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">2 <strong>\u5217\u8868\u722c\u53d6\u5957\u8def\u2014\u2014\u6a21\u62df\u65b0\u95fb\u5217\u8868\u7684\u6807\u9898\u4e0e\u94fe\u63a5<\/strong>\uff08\u79bb\u7ebf\u53ef\u8dd1\uff09\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>html = \"\"\"\n&lt;div id=\"news\"&gt;\n  &lt;dl&gt;&lt;dd&gt;&lt;a href=\"\/n1\"&gt;\u66b4\u96e8\u6a59\u8272\u9884\u8b66\u53d1\u5e03&lt;\/a&gt;&lt;span&gt;10:25&lt;\/span&gt;&lt;\/dd&gt;&lt;\/dl&gt;\n  &lt;dl&gt;&lt;dd&gt;&lt;a href=\"\/n2\"&gt;\u5317\u4eac\u96e8\u540e\u95f7\u70ed\u6301\u7eed&lt;\/a&gt;&lt;span&gt;11:29&lt;\/span&gt;&lt;\/dd&gt;&lt;\/dl&gt;\n&lt;\/div&gt;\n\"\"\"\n\nsoup = BeautifulSoup(html, \"html.parser\")\nitems = soup.select(\"#news dl\")            # \u7b2c\u4e00\u6b65\uff1a\u6240\u6709\u6761\u76ee\nprint(f\"\u5171 {len(items)} \u6761\")\nfor item in items:                         # \u7b2c\u4e8c\u6b65\uff1a\u9010\u6761\u53d6\u5b57\u6bb5\n    title = item.select_one(\"a\").get_text(strip=True)\n    href = item.select_one(\"a\")&#91;\"href\"]\n    print(title, \"-&gt;\", href)\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\"><code>soup.select(\"#news dl\")<\/code> \u7528 id \u9009\u62e9\u5668\u5b9a\u4f4d\u5bb9\u5668\uff0c\u53d6\u91cc\u9762\u6240\u6709 <code>dl<\/code> \u6761\u76ee\uff1b\u5faa\u73af\u91cc <code>item.select_one(\"a\")<\/code> \u53d6\u7b2c\u4e00\u6761\u94fe\u63a5\uff0c<code>get_text(strip=True)<\/code> \u62ff\u6807\u9898\u3001<code>[\"href\"]<\/code> \u62ff\u94fe\u63a5\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u6613\u9519\u70b9<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u9519\u8bef\u5199\u6cd5\uff1a\u9700\u8981\u5355\u4e2a\u5374\u7528 <code>select<\/code> \u2192 \u95ee\u9898\uff1a\u8fd4\u56de\u5217\u8868\uff0c<code>.get_text()<\/code> \u62a5\u9519 \u2192 \u6b63\u786e\u5199\u6cd5\uff1a\u53ea\u8981\u4e00\u4e2a\u7528 <code>select_one<\/code>\uff0c\u8981\u5168\u90e8\u7528 <code>select<\/code>\u3002<\/li>\n\n\n\n<li>\u9519\u8bef\u5199\u6cd5\uff1aclass \u6f0f\u5199 <code>.<\/code> \u2192 \u95ee\u9898\uff1a\u6309\u6807\u7b7e\u540d\u627e\uff0c\u5339\u914d\u4e0d\u5230 \u2192 \u6b63\u786e\u5199\u6cd5\uff1aclass \u524d\u5fc5\u987b\u6709\u70b9\uff1a<code>p.wea<\/code>\uff1bid \u7528 <code>#<\/code>\u3002<\/li>\n\n\n\n<li>\u9519\u8bef\u5199\u6cd5\uff1a\u5185\u5c42\u4e5f\u7528 <code>select(\"a\")<\/code> \u2192 \u95ee\u9898\uff1a\u62ff\u5230\u5217\u8868\uff0c<code>[\"href\"]<\/code> \u62a5\u9519 \u2192 \u6b63\u786e\u5199\u6cd5\uff1a\u6bcf\u9879\u53ea\u8981\u4e00\u4e2a\uff0c\u5185\u5c42\u7528 <code>select_one<\/code>\u3002<\/li>\n\n\n\n<li>\u9519\u8bef\u5199\u6cd5\uff1a\u94fe\u63a5\u662f\u76f8\u5bf9\u8def\u5f84\uff08<code>\/n1<\/code>\uff09 \u2192 \u95ee\u9898\uff1a\u76f4\u63a5\u62fc\u63a5\u4e22\u57df\u540d \u2192 \u6b63\u786e\u5199\u6cd5\uff1a\u62fc\u5168\uff1a<code>\"https:\/\/example.com\" + href<\/code>\u3002<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u8bb0\u5fc6\u53e3\u8bc0<\/strong>\uff1aselect \u4e00\u5806 select_one \u4e00\u4e2a\uff1b# \u662f id\uff0c. \u662f class\uff0c\u7a7a\u683c\u662f\u300c\u91cc\u9762\u7684\u300d\uff1b\u5217\u8868\u5148\u9009\u6761\u76ee\u518d\u53d6\u5b57\u6bb5\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">4 robots.txt \u4e0e\u541b\u5b50\u534f\u8bae \u2014\u2014 \u505a\u4e2a\u6709\u793c\u8c8c\u7684\u722c\u866b<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u662f\u4ec0\u4e48\uff1f\u4e3a\u4ec0\u4e48\u5b66\uff1f<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>robots.txt \u662f\u7f51\u7ad9\u653e\u5728\u6839\u76ee\u5f55\u7684\u300c\u8bf4\u660e\u6587\u4ef6\u300d<\/strong>\uff0c\u544a\u8bc9\u722c\u866b\u54ea\u4e9b\u8def\u5f84\u53ef\u4ee5\u722c\u3001\u54ea\u4e9b\u4e0d\u53ef\u4ee5\u3002\u5199\u722c\u866b\u524d\u5148\u770b\u5b83\u3001\u9075\u5b88\u5b83\uff0c\u914d\u5408 <code>time.sleep<\/code> \u63a7\u5236\u9891\u7387\uff0c\u662f\u722c\u866b\u5de5\u7a0b\u5e08\u7684\u57fa\u672c\u7d20\u517b\u2014\u2014\u4e71\u722c\u4f1a\u88ab\u5c01 IP\uff0c\u751a\u81f3\u60f9\u4e0a\u5b98\u53f8\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u5e95\u5c42\u539f\u7406<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">robots.txt \u89c4\u5219\uff1a<code>User-agent<\/code> \u58f0\u660e\u9488\u5bf9\u54ea\u4e2a\u722c\u866b\uff08<code>*<\/code> \u8868\u793a\u6240\u6709\uff09\uff1b<code>Disallow<\/code> \u7981\u6b62\u8bbf\u95ee\u7684\u8def\u5f84\uff1b<code>Allow<\/code> \u4f8b\u5916\u5141\u8bb8\u3002\u541b\u5b50\u534f\u8bae\u662f\u793e\u533a\u7ea6\u5b9a\u800c\u975e\u6cd5\u5f8b\uff1a\u6709 robots \u5c31\u9075\u5b88\u3001\u63a7\u5236\u9891\u7387\uff08\u6bcf\u8bf7\u6c42\u95f4\u9694\u51e0\u79d2\uff09\u3001\u6570\u636e\u53ea\u7528\u4e8e\u5b66\u4e60\u7814\u7a76\u3001\u4e0d\u5546\u7528\u4e0d\u516c\u5f00\u4f20\u64ad\u3001\u7f51\u7ad9\u660e\u786e\u53cd\u5bf9\u5c31\u505c\u6b62\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u751f\u6d3b\u7c7b\u6bd4<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u50cf<strong>\u56fe\u4e66\u9986\u89c4\u5219<\/strong>\uff1arobots.txt \u662f\u95e8\u53e3\u300c\u5165\u9986\u987b\u77e5\u300d\uff0c\u541b\u5b50\u534f\u8bae\u662f\u300c\u5b89\u9759\u3001\u4e0d\u5360\u5ea7\u300d\u7684\u516c\u5171\u793c\u4eea\u3002\u4f60\u4e0d\u8fdd\u6cd5\uff0c\u4f46\u6ca1\u793c\u8c8c\u4f1a\u88ab\u7ba1\u7406\u5458\u76ef\u4e0a\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u6ce8\u610f\u4e8b\u9879\u603b\u7ed3<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">1 <strong>\u67e5\u770b\u76ee\u6807\u7f51\u7ad9\u7684 robots.txt<\/strong>\uff08\u9700\u8981\u8054\u7f51\uff09\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>import requests\n\nresp = requests.get(\"https:\/\/www.weather.com.cn\/robots.txt\", timeout=5)\nprint(\"\u72b6\u6001\u7801\uff1a\", resp.status_code)\nprint(resp.text&#91;:200])      # \u6709\u5185\u5bb9\u5c31\u8bf4\u660e\u7f51\u7ad9\u58f0\u660e\u4e86\u89c4\u5219\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u76f4\u63a5\u8bf7\u6c42 robots \u6587\u4ef6\uff0c<code>resp.text<\/code> \u6253\u5370\u5185\u5bb9\u3002<strong>\u6ce8\u610f\uff1a\u90e8\u5206\u7f51\u7ad9\u6ca1\u6709 robots.txt\uff08\u8fd4\u56de 404\uff09\uff0c\u4f46\u6ca1\u58f0\u660e\u4e0d\u4ee3\u8868\u53ef\u4ee5\u968f\u4fbf\u722c<\/strong>\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">2 <strong>\u9891\u7387\u63a7\u5236 + \u5f02\u5e38\u515c\u5e95\u7684\u6807\u51c6\u59ff\u52bf<\/strong>\uff08\u79bb\u7ebf\u53ef\u8dd1\uff09\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>import time\n\nurls = &#91;\"https:\/\/example.com\/page1\", \"https:\/\/example.com\/page2\"]\nfor url in urls:\n    try:\n        print(f\"\u6293\u53d6\uff1a{url}\uff08\u6a21\u62df\u6210\u529f\uff09\")\n    except Exception as e:       # \u5b9e\u9645\u5e94\u63a5\u4f4f requests \u7684\u5177\u4f53\u5f02\u5e38\n        print(f\"\u6293\u53d6\u5931\u8d25\uff1a{e}\")\n    time.sleep(2)                # \u6bcf\u6b21\u8bf7\u6c42\u540e\u4f11\u606f 2 \u79d2\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\"><code>time.sleep(2)<\/code> \u662f<strong>\u9891\u7387\u63a7\u5236<\/strong>\u6838\u5fc3\u2014\u2014\u6bcf\u8bf7\u6c42\u4e00\u6b21\u505c 2 \u79d2\uff0c\u4e0d\u7ed9\u670d\u52a1\u5668\u538b\u529b\uff1b<code>try\/except<\/code> \u628a\u5355\u4e2a\u5931\u8d25\u515c\u4f4f\uff0c<strong>\u4e00\u4e2a\u5931\u8d25\u4e0d\u5f71\u54cd\u540e\u9762<\/strong>\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u6613\u9519\u70b9<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u9519\u8bef\u5199\u6cd5\uff1a\u5faa\u73af\u51e0\u767e\u4e2a URL \u4e0d sleep \u2192 \u95ee\u9898\uff1a\u77ac\u95f4\u6253\u7206\u670d\u52a1\u5668\uff0cIP \u88ab\u5c01 \u2192 \u6b63\u786e\u5199\u6cd5\uff1a\u6bcf\u6b21\u8bf7\u6c42\u540e <code>time.sleep(1~3)<\/code>\u3002<\/li>\n\n\n\n<li>\u9519\u8bef\u5199\u6cd5\uff1a\u5b8c\u5168\u4e0d\u770b robots.txt \u2192 \u95ee\u9898\uff1a\u53ef\u80fd\u722c\u5230\u7981\u6b62\u8def\u5f84 \u2192 \u6b63\u786e\u5199\u6cd5\uff1a\u8bf7\u6c42\u524d\u5148\u8bfb <code>\u76ee\u6807\u7f51\u7ad9\/robots.txt<\/code>\u3002<\/li>\n\n\n\n<li>\u9519\u8bef\u5199\u6cd5\uff1a\u4e00\u4e2a\u9875\u9762\u5931\u8d25\u5c31\u5d29\u6e83 \u2192 \u95ee\u9898\uff1a\u4e00\u4e2a 404 \u4e2d\u65ad\u5168\u90e8\u4efb\u52a1 \u2192 \u6b63\u786e\u5199\u6cd5\uff1a<code>try\/except<\/code> \u63a5\u4f4f\uff0c\u7ee7\u7eed\u4e0b\u4e00\u4e2a\u3002<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u8bb0\u5fc6\u53e3\u8bc0<\/strong>\uff1a\u5148\u770b robots \u518d\u52a8\u624b\uff0csleep \u63a7\u9891\u4e0d\u8f70\u70b8\uff1bexcept \u515c\u5e95\u4e0d\u5d29\u6e83\uff0c\u541b\u5b50\u534f\u8bae\u8bb0\u5fc3\u95f4\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">5 \u52a8\u624b\u5b9e\u8df5\uff1a\u722c\u53d6\u65b0\u95fb\u5217\u8868\u5e76\u4fdd\u5b58 CSV<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">\u722c\u53d6\u4e2d\u56fd\u5929\u6c14\u7f51\u9996\u9875\u7684\u300c\u5929\u6c14\u8d44\u8baf\u300d\u65b0\u95fb\u5217\u8868\uff08\u6807\u9898\u3001\u94fe\u63a5\u3001\u6765\u6e90\u3001\u65f6\u95f4\uff09\uff0c\u4fdd\u5b58\u6210 CSV\uff0c\u65b9\u4fbf\u540e\u7eed\u5206\u6790\u6216\u751f\u6210\u62a5\u544a\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code># news_crawler.py \u2014\u2014 \u5929\u6c14\u8d44\u8baf\u65b0\u95fb\u5217\u8868\u722c\u866b\nimport csv\nimport time\nimport requests\nfrom bs4 import BeautifulSoup\n\nheaders = {\n    \"User-Agent\": \"Mozilla\/5.0 (Windows NT 10.0; Win64; x64) \"\n                  \"AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/120.0 Safari\/537.36\"\n}\n\nurl = \"https:\/\/www.weather.com.cn\/weather\/101010100.shtml\"\n\ndef crawl_news():\n    news_list = &#91;]\n    try:\n        resp = requests.get(url, headers=headers, timeout=10)\n        resp.raise_for_status()\n        resp.encoding = \"utf-8\"\n        soup = BeautifulSoup(resp.text, \"html.parser\")\n\n        for item in soup.select(\"#tq_zx dl\"):\n            a = item.select_one(\"dd a\")\n            if not a:\n                continue\n            title = a.get_text(strip=True)\n            href = a&#91;\"href\"]\n            # \u6765\u6e90\u548c\u65f6\u95f4\u5728\u540c\u4e00\u884c\uff0c\u5982\"\u4e2d\u56fd\u5929\u6c14\u7f51   2026-08-03 11:29\"\n            source_line = item.select_one(\"dd span\").get_text(strip=True)\n            parts = source_line.split()\n            source = parts&#91;0] if parts else \"\"\n            pub_time = parts&#91;1] if len(parts) &gt; 1 else \"\"\n            news_list.append(&#91;title, href, source, pub_time])\n\n    except requests.exceptions.RequestException as e:\n        print(f\"\u8bf7\u6c42\u5931\u8d25\uff1a{e}\")\n    except AttributeError:\n        print(\"\u9875\u9762\u7ed3\u6784\u53ef\u80fd\u6539\u7248\u4e86\uff0c\u8bf7\u68c0\u67e5\u9009\u62e9\u5668\")\n\n    return news_list\n\ndef save_csv(news_list):\n    with open(\"news_list.csv\", \"w\", newline=\"\", encoding=\"utf-8\") as f:\n        writer = csv.writer(f)\n        writer.writerow(&#91;\"\u6807\u9898\", \"\u94fe\u63a5\", \"\u6765\u6e90\", \"\u65f6\u95f4\"])\n        writer.writerows(news_list)\n    print(f\"\u5df2\u4fdd\u5b58 {len(news_list)} \u6761\u65b0\u95fb\u5230 news_list.csv\")\n\nif __name__ == \"__main__\":\n    news = crawl_news()\n    for n in news&#91;:3]:\n        print(n&#91;0], \"|\", n&#91;2], n&#91;3])\n    save_csv(news)\n    time.sleep(1)\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u8fd0\u884c\u6548\u679c\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>\u5317\u4eac\u96e8\u540e\u6e7f\u6f09\u6f09 \u6851\u62ff\u5929\u5a01\u529b\u4e0d\u51cf | \u4e2d\u56fd\u5929\u6c14\u7f51 2026-08-03 11:29\n\u6cb3\u5317\u5927\u8303\u56f4\u964d\u96e8\u6301\u7eed \u4eca\u5929\u77f3\u5bb6\u5e84\u5f20\u5bb6\u53e3\u627f\u5fb7\u7b49\u5730\u96e8\u52bf\u731b\u70c8 | \u4e2d\u56fd\u5929\u6c14\u7f51 2026-08-03 10:56\n\u66b4\u96e8\u6a59\u8272\u9884\u8b66\uff1a\u9655\u897f\u91cd\u5e86\u7b495\u7701\u533a\u5e02\u90e8\u5206\u5730\u533a\u6709\u5927\u66b4\u96e8 \u5c40\u5730\u7279\u5927\u66b4\u96e8 | \u4e2d\u56fd\u5929\u6c14\u7f51 2026-08-03 10:25\n\u5df2\u4fdd\u5b58 5 \u6761\u65b0\u95fb\u5230 news_list.csv\n<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">\u6253\u5f00 <code>news_list.csv<\/code> \u9a8c\u8bc1\u6570\u636e\u3002\u6574\u4e2a\u7a0b\u5e8f\u5c31\u662f\u4e00\u4e2a\u6807\u51c6\u7684\u722c\u866b\u95ed\u73af\uff1a<strong>\u8bf7\u6c42 \u2192 \u89e3\u6790 \u2192 \u63d0\u53d6 \u2192 \u4fdd\u5b58 \u2192 \u4f11\u606f<\/strong>\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u5347\u7ea7\u6311\u6218<\/strong>\uff1a\u628a <code>news_list.csv<\/code> \u91cc\u7684\u65b0\u95fb\u94fe\u63a5\u9010\u4e2a\u8bf7\u6c42\u4e00\u904d\uff0c\u6293\u53d6\u6bcf\u7bc7\u65b0\u95fb\u7684\u6b63\u6587\u524d 200 \u5b57\uff08\u8bb0\u5f97\u6bcf\u6b21 <code>time.sleep(2)<\/code>\uff0c\u5e76\u5224\u65ad\u9875\u9762\u7ed3\u6784\uff09\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u4eca\u65e5\u603b\u7ed3<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><code>requests.get()<\/code> \u62ff\u7f51\u9875\uff1a<code>status_code<\/code> \u770b\u6210\u8d25\u3001<code>resp.text<\/code> \u662f\u6e90\u7801\u3001<code>resp.encoding<\/code> \u7ba1\u4e2d\u6587\u4e0d\u4e71\u7801\uff0c<code>timeout<\/code> \u9632\u5361\u6b7b\nBeautifulSoup \u5bf9\u8c61\u6811\uff1a<code>find<\/code> \/ <code>find_all<\/code> \/ <code>get_text()<\/code> \/ <code>[\"\u5c5e\u6027\"]<\/code>\uff0c<code>class_<\/code> \u5e26\u4e0b\u5212\u7ebf\nCSS \u9009\u62e9\u5668\uff1a<code>select<\/code> \u4e00\u5806\u3001<code>select_one<\/code> \u4e00\u4e2a\uff0c<code>#id<\/code>\u3001<code>.class<\/code>\u3001<code>ul.t li<\/code> \u540e\u4ee3\u9009\u62e9\n\u5217\u8868\u722c\u53d6\u5957\u8def\uff1a\u5916\u5c42 <code>select<\/code> \u62ff\u6761\u76ee\uff0c\u5185\u5c42 <code>select_one<\/code> \u53d6\u5b57\u6bb5\uff0c<code>strip=True<\/code> \u53bb\u7a7a\u767d\n\u722c\u866b\u89c4\u77e9\uff1a\u5148\u770b robots.txt\u3001<code>time.sleep<\/code> \u63a7\u9891\u3001<code>try\/except<\/code> \u515c\u5e95\uff0c\u505a\u4e2a\u6709\u793c\u8c8c\u7684\u8bbf\u5ba2\n\u5b8c\u6574\u95ed\u73af\uff1a\u8bf7\u6c42 \u2192 \u89e3\u6790 \u2192 \u63d0\u53d6 \u2192 \u4fdd\u5b58 CSV \u2192 \u4f11\u606f\uff0c\u722c\u866b\u5165\u95e8\u8fbe\u6210<\/p>\n\n\n\n<figure class=\"wp-block-table\"><table class=\"has-fixed-layout\"><thead><tr><th>\u62a5\u9519<\/th><th>\u539f\u56e0<\/th><th>\u4fee\u590d<\/th><\/tr><\/thead><tbody><tr><td><code>ModuleNotFoundError: No module named 'requests'<\/code><\/td><td>\u6ca1\u5b89\u88c5 requests<\/td><td>\u547d\u4ee4\u884c\u6267\u884c <code>pip install requests beautifulsoup4<\/code><\/td><\/tr><tr><td><code>requests.exceptions.ConnectTimeout<\/code> \/ <code>ConnectionError<\/code><\/td><td>\u8fde\u4e0d\u4e0a\u7f51\u7ad9\uff08\u65ad\u7f51\u3001\u57df\u540d\u9519\u8bef\u3001\u88ab\u5899\uff09<\/td><td>\u68c0\u67e5\u7f51\u7edc\uff0c\u786e\u8ba4 URL \u80fd\u6b63\u5e38\u8bbf\u95ee\uff0c\u5fc5\u8981\u65f6\u914d\u7f6e\u4ee3\u7406<\/td><\/tr><tr><td>\u722c\u4e0b\u6765\u7684\u4e2d\u6587\u5168\u662f\u4e71\u7801<\/td><td>\u7f51\u9875\u7f16\u7801\u6ca1\u8bbe\u7f6e\u5bf9<\/td><td>\u624b\u52a8\u6307\u5b9a <code>resp.encoding = \"utf-8\"<\/code>\uff08\u6216\u7f51\u9875\u58f0\u660e\u7684\u5176\u5b83\u7f16\u7801\uff09<\/td><\/tr><tr><td><code>AttributeError: 'NoneType' object has no attribute 'get_text'<\/code><\/td><td><code>select_one<\/code> \u6ca1\u5339\u914d\u5230\u5185\u5bb9\uff0c\u8fd4\u56de <code>None<\/code><\/td><td>\u6253\u5370 <code>soup.select(...)<\/code> \u68c0\u67e5\u9875\u9762\u7ed3\u6784\u662f\u5426\u6539\u7248\uff0c\u4fee\u6b63\u9009\u62e9\u5668<\/td><\/tr><tr><td><code>HTTPError 403<\/code> \u6216\u9891\u7e41\u88ab\u9650\u6d41<\/td><td>\u7f51\u7ad9\u8bc6\u522b\u51fa\u662f\u722c\u866b<\/td><td>\u52a0 <code>User-Agent<\/code> \u8bf7\u6c42\u5934\uff0c\u964d\u4f4e\u9891\u7387\uff0c\u9075\u5b88 robots.txt<\/td><\/tr><\/tbody><\/table><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>1 requests \u4e0e Response \u5bf9\u8c61 \u2014\u2014 \u722c\u866b\u7684\u7b2c\u4e00\u6b65 \u662f\u4ec0\u4e48\uff1f\u4e3a\u4ec0\u4e48\u5b66\uff1f requests \u662f [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_import_markdown_pro_load_document_selector":0,"_import_markdown_pro_submit_text_textarea":"","footnotes":""},"categories":[16,9],"tags":[17],"class_list":["post-119","post","type-post","status-publish","format-standard","hentry","category-python","category-code-dev","tag-python-day"],"_links":{"self":[{"href":"https:\/\/ltrainyard.icu\/index.php\/wp-json\/wp\/v2\/posts\/119","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ltrainyard.icu\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ltrainyard.icu\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ltrainyard.icu\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/ltrainyard.icu\/index.php\/wp-json\/wp\/v2\/comments?post=119"}],"version-history":[{"count":2,"href":"https:\/\/ltrainyard.icu\/index.php\/wp-json\/wp\/v2\/posts\/119\/revisions"}],"predecessor-version":[{"id":155,"href":"https:\/\/ltrainyard.icu\/index.php\/wp-json\/wp\/v2\/posts\/119\/revisions\/155"}],"wp:attachment":[{"href":"https:\/\/ltrainyard.icu\/index.php\/wp-json\/wp\/v2\/media?parent=119"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ltrainyard.icu\/index.php\/wp-json\/wp\/v2\/categories?post=119"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ltrainyard.icu\/index.php\/wp-json\/wp\/v2\/tags?post=119"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}